Security & Cryptography · Computer Science & AI
Cryptography & Security
The newest papers in Cryptography & Security that ReadSearch has read, newest first. Each links to its own page, with its authors, date, where it was published and the original.
1,372 papers, from 4 September 2026 to 5 November 2026: 1,372 arXiv preprints.
Get the few papers worth your time in Cryptography & Security every morning.
Follow Cryptography & Security and ReadSearch reads its new papers each day, then brings you the few worth reading, each with its key finding in a sentence.
Newest papers, page 28
Declared but Unaccountable: Measuring the Seller-Identity Gap in Advertising Supply-Chain Transparency
Public advertising transparency relies on a minimum accountability condition: an account authorized by a publisher in ads$.$txt or app-ads$.$txt should appear in the applicable sellers$.$json…Towards Merging-conditional Backdoor Unalignment against Large Language Models
Model merging has become widely adopted for enhancing the task-specific performance of Large Language Models (LLMs) without additional training.Last Secure Code Benchmark: Is the Code You Vibe Secure?
AI coding agents now write much of the code that ships, yet whether that code is secure remains unclear.KedgeFlow: A Programmable Control Plane for Enterprise AI Agents
Enterprise AI agents can execute altered versions of approved actions, concurrently reuse the same permission, or retry operations whose responses were lost.SEEK: Agentic Knowledge Graph Retrieval for Secure Code Generation
Large Language Models (LLMs) can generate functionally correct code while introducing exploitable security weaknesses, particularly when developers specify functionality without explicit security…GAMW: Generation-Aware Mel-Domain Watermarking for TTS Traceability
As text-to-speech (TTS) systems continue to advance, provenance tracking and security verification of synthesized speech have become increasingly important.When the Approved File Is Unchanged: Authority-Set Integrity for Deployment and Coding-Agent Approvals
An approval for a deployment, a release, or an agent-issued command is recorded against one object: a workflow file, a script, a command line.Can agents whose sole duty is to keep humans alive be hijacked to kill? Delayed multi-turn derived-action trap attacks in simulated high-stakes environments
We ask whether a tool-using agent whose sole duty is to keep humans alive can be induced, by delayed prompt injection, to kill.Only What You've Signed up For: Secure Workflows with Constrained Diffusion Agents
As agentic AI systems take on increasingly complex and consequential tasks, securing them against prompt injection becomes critical.Exploring Jailbreak Vulnerability Across Depth-Based Dynamic Inference in Large Language Models
Large Language Models (LLMs) have been shown to be computationally expensive and vulnerable to jailbreak attacks, in which adversarial prompts bypass safety alignment and induce harmful responses.Reward Hacking as a Transmissible Strategy in Multi-Agent Coding Systems
Multi-agent systems are increasingly used to solve coding tasks by coordinating agents that share code and plans.The False Allure of "Security by Obscurity": A Game-Theoretic Approach
"Security by obscurity," or the idea that hiding how a system works helps protect it from adversaries, has long been poorly regarded in the security community.Vulnerable Models in the AI Supply Chain: An Empirical Study of Adoption, Propagation, and Usage Patterns
The rapid integration of Artificial Intelligence (AI) models has established a complex supply chain, but many of these shared artifacts harbor severe vulnerabilities such as insecure serialization…WaveMark: Robust Wavelet-Domain Image Watermarking for Diffusion Models
Image watermarking enables provenance tracing for photorealistic images generated by diffusion models.Space Over Statistic, Retraining Over Ranking: Auditing Training Labels Under Label-Only Backdoors
Some backdoor attacks never touch an image.CAPE - Context-Aware Prioritization Engine for Vulnerability Scoring and Management
Vulnerability patching is critical for safeguarding an enterprise's software ecosystem from cyber attacks.The Limits of Query Monitoring against Distributed Model Extraction
Model providers now face distillation campaigns run through thousands of accounts, each of which looks like an ordinary user.Understanding Verification Vulnerabilities in Cross-chain Bridges: An Empirical Study
With the rapid development of blockchain technology, numerous heterogeneous blockchains have emerged, each featuring distinct architectures, consensus mechanisms, and application ecosystems.Understanding and Mitigating Cross-Session Attacks via Persistent Artifacts in Agent Skill Composition
Agent skills extend the capabilities of AI agents by bundling instructions, code, and resources into reusable packages.LETHE: Defending against Unauthorized Image-to-Video Generation via Value Diversity Collapse
Image-to-video (I2V) diffusion models can animate a single reference image into high-quality, subject-consistent videos, posing threats of misuse as anyone can turn personal photos into fabricated…